Metraipolis › archive › dc_0259efd46dc5

PAGE: Partition-Aware Gated KV-Cache Eviction — arXiv:2609.22157

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22157
License (as archived)
CC0-1.0
Archived
2026-10-09T06:50:22.484Z
SHA-256 of the archived text
e507f903ea8f25e7f734ab0ffe16ea67f5acd48e3719809ded31adcc98e328a4
Stable URL of this page
https://metraipolis.com/documento/dc_0259efd46dc5

How to cite

PAGE: Partition-Aware Gated KV-Cache Eviction — arXiv:2609.22157 — arXiv (en), https://arxiv.org/abs/2609.22157 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0259efd46dc5 (Metraipolis archive dc_0259efd46dc5, sha256 e507f903ea8f25e7f734ab0ffe16ea67f5acd48e3719809ded31adcc98e328a4)
BibTeX
@misc{dc0259efd46dc5,
  title = {PAGE: Partition-Aware Gated KV-Cache Eviction — arXiv:2609.22157},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22157},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0259efd46dc5; sha256 e507f903ea8f25e7f734ab0ffe16ea67f5acd48e3719809ded31adcc98e328a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22157. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

KV-cache eviction can do more than compress. In long-context LLMs, keeping only some cached tokens sometimes matches or exceeds full-cache accuracy, because many redundant prefill tokens otherwise dilute attention away from the tokens that carry the answer. This benefit is not uniform, and evicting the wrong tokens can drop accuracy to zero on tasks that require precise retrieval, so the useful question is not only which tokens to keep but also whether to evict this input at all. We show that one label-free number computed from the prefill attention, the drop between early and late layers in how much attention heads agree on which tokens to read, predicts per input, before any decoding, which of the two cases an input falls under. We build this into PAGE (Partition-Aware Gated Eviction), a wrapper that runs any SnapKV-style evictor when the drop is large and keeps the full cache when it is small, with no training, labels, or fine-tuning. PAGE is a safety mechanism rather than a compressor, so we measure it by the failures it prevents. It cuts the harm rate on capacity-bound inputs from 0.75 to 0.026, and on multi-key retrieval with Mistral-7B plain SnapKV falls from 99\% to 0\% as the budget shrinks, while PAGE holds it at 89\%. Elsewhere, it passes the base evictor through unchanged, which is the intended behaviour and is what we observe in 8 of 16 cells. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL); Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.22157 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:48:45.088Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).